Retrieving information from microblog using pattern mining and relevance feedback

Retrieving information from Twitter is always challenging due to its large volume, inconsistent writing and noise. Most existing information retrieval (IR) and text mining methods focus on term-based approach, but suffers from the problems of terms variation such as polysemy and synonymy. This problem deteriorates when such methods are applied on Twitter due to the length limit. Over the years, people have held the hypothesis that pattern-based methods should perform better than term-based methods as it provides more context, but limited studies have been conducted to support such hypothesis especially in Twitter. This paper presents an innovative framework to address the issue of performing IR in microblog. The proposed framework discover patterns in tweets as higher level feature to assign weight for low-level features (i.e. terms) based on their distributions in higher level features. We present the experiment results based on TREC11 microblog dataset and shows that our proposed approach significantly outperforms term-based methods Okapi BM25, TF-IDF and pattern based methods, using precision, recall and F measures.

Weibo, framing, and media practices in China

This study uses frames analysis to investigate online discourses and processes of political deliberation on China’s weibo (microblog) service. It offers a comparative analysis of competing discourses surrounding the case of Wang Yue, a toddler who was ran over by two motor vehicles in Foshan, following which eighteen people passed by and ignored her plight. The study aims to understand how weibo facilitate its users to express their differences and deliberate disagreements with each other. The study found that Internet users are rational in the sense that they do not simply lean towards a dichotomised choice of ‘pro-’ or ‘anti-’ official discourse, but they are able to negotiate their moral choices by considering a wide range of social and political factors in such an emotional and morally controversial incident.

Learning in 140 characters : microblogging for professional learning

This thesis investigated how microblogging, a form of online social networking, was being employed by educators to support their professional learning. The study found that educators who participate in microblogging engage in a wide range of behaviours, with certain behaviours and activities commonly exhibited. An advantage of microblogging as a professional learning tool is its ability to link educators globally to exchange ideas from different perspectives and to share resources and teaching practices. Educators who microblog have access to relevant and timely learning that is not constrained by time or distance and can be tailored to meet their individual needs.

Detecting news topics from microblogs using sequential pattern mining

This thesis presents a sequential pattern based model (PMM) to detect news topics from a popular microblogging platform, Twitter. PMM captures key topics and measures their importance using pattern properties and Twitter characteristics. This study shows that PMM outperforms traditional term-based models, and can potentially be implemented as a decision support system. The research contributes to news detection and addresses the challenging issue of extracting information from short and noisy text.